Semi-Supervised Classification with Graph Convolutional Networks

TL;DR

This paper introduces a scalable graph convolutional network method for semi-supervised learning on graph data, effectively capturing local structure and node features, and demonstrating superior performance on citation and knowledge graph datasets.

Contribution

The paper proposes a novel, efficient graph convolutional architecture that scales linearly with edges and improves semi-supervised classification accuracy.

Findings

Outperforms related methods on citation networks

Scales linearly with graph edges

Encodes local structure and node features effectively

Abstract

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.